Semantic search

Search that finds results based on the meaning of a query, so it works even when the query and the document use completely different words.

Traditional keyword search requires the document to contain the exact words you typed. Semantic search uses embeddings (numerical meaning-representations) to understand that a query like "onboarding" should match documents that say "activation," "first session," or "getting started," because the underlying meaning is similar. Users can search in their own words and still find relevant results, even when the source material uses different terminology.

Builder example

Your users rarely know the exact terms the documents use. A sales rep searching for "discount approval process" needs to find the document titled "pricing exception workflow." Semantic search bridges that vocabulary gap. The tradeoff: it can miss exact matches that keyword search would catch instantly, like a specific error code or product SKU. Most production systems combine both approaches.

A customer searches for 'how do I get a refund' and finds nothing because the help doc is titled 'return and exchange policy.' Keyword search requires the exact word.

Use semantic search so meaning-based queries find the right docs. Combine it with keyword search to also catch exact terms like error codes and product names.

Common confusion: Semantic search finds meaning-similar results, which sometimes means it returns topically related content that does not answer the question. A query for "refund policy" might surface a document about "return shipping" because the meanings are close, even though the content differs.